Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA taaft Grounded question answering systems should answer only when the supplied evidence supports the answ… 2026-09-01 published
Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction taaft We present, to the best of our knowledge, the first publicly available resource for predicting left… 2026-09-02 published
Learning from Simulated and Unsupervised Images through Adversarial Training Apple With recent progress in graphics, it has become more tractable to train models on synthetic images,… 2016-12-22 published
Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar taaft Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar,… 2026-09-04 published
Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval taaft In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive simila… 2026-08-31 published
Learning Human Health and Diseases from 24-hour Wrist Movement taaft Much of human health and function unfolds beyond the clinic, through the movements of everyday life… 2026-08-30 published
Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds Microsoft Understanding humans from LiDAR point clouds is one of the most critical tasks in autonomous drivin… 2026-03-17 published
Learning Materials Properties from Scarce Labels and Unlabeled Crystals taaft Learning materials properties from scarce labels and unlabeled crystals is a central challenge for… 2026-08-31 published
Learning Multiagent Communication with Backpropagation taaft Many tasks in AI require the collaboration of multiple agents. Typically, the communication protoco… 2016-05-25 published
Learning New Facts with QLoRA: An Acquisition-Retention Frontier taaft Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it upd… 2026-08-26 published
Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees taaft Token prediction is a central pre-training objective for modern language models. Despite its empiri… 2026-08-30 published
Learning Spatial-Spectral Refinement and Calibrating Complementary Observations for Hyperspectral Image Super-Resolution taaft Hyperspectral and multispectral image fusion (HMIF) aims to reconstruct a high-resolution hyperspec… 2026-09-04 published
Learning Spectral-Like Mesh-Free Discretisations taaft Meshfree methods such as smoothed particle hydrodynamics (SPH) with kernel corrections, radial basi… 2026-09-02 published
Learning Task-Specific Antibody Representations via Function-Aware Masking taaft Antibody-specific language models pretrained via masked language modeling (MLM) learn representatio… 2026-09-01 published
Learning the Constitutive Behavior of Materials via Neural Operators and Causal Attention: Case Studies in Plasticity and Damage taaft Classical constitutive modeling of path-dependent inelastic materials relies on internal state vari… 2026-09-02 published
Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory taaft Kohn--Sham density functional theory (DFT) underpins electronic-structure simulations, but repeated… 2026-08-24 published
Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing taaft Cross-modal image translation in remote sensing must preserve source-observed content while matchin… 2026-08-28 published
Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning taaft Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises use… 2026-08-28 published
Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face) taaft Face recognition in unconstrained environments remains highly challenging due to diverse and extrem… 2026-09-02 published
Learning to Commit: Generating Organic Pull Requests via Online Repository Memory taaft Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks… 2026-03-27 published
Learning to Compress Prompts with Gist Tokens taaft Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but pr… 2023-04-17 published
Learning to Difference: Adaptive Reversible Differencing (AdaRDiff) for Time Series Forecasting taaft Reliable long-horizon time series forecasting is an important yet difficult problem. Trends and sea… 2026-08-28 published
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents taaft Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows,… 2026-08-31 published
Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis taaft Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to m… 2026-09-02 published
Learning to Optimize Joint Source and RIS-assisted Channel Encoding for Multi-User Semantic Communication Systems taaft In this paper, we explore a joint source and reconfigurable intelligent surface (RIS)-assisted chan… 2026-03-22 published
Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems taaft Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinatio… 2026-08-31 published
Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models taaft Image restoration models are typically trained with a fixed set of capabilities. When new restorati… 2026-08-31 published
Learning to Retrieve from Agent Trajectories taaft Information retrieval (IR) systems have traditionally been designed and trained for human users, wi… 2026-03-30 published
Learning to Track from Privileged Target Appearances taaft Target templates define what a visual tracker searches for, yet the templates available at inferenc… 2026-09-02 published
Learning to Trim: End-to-End Causal Graph Pruning with Dynamic Anatomical Feature Banks for Medical VQA taaft Medical Visual Question Answering (MedVQA) models often exhibit limited generalization due to relia… 2026-03-27 published
Learning to Zoom Efficiently with a Contrastive Curriculum taaft Using a zoom-in tool is an important foundational part of modern visual agents, because it allows t… 2026-09-02 published
Learning Trajectory-Aware Multimodal Large Language Models for Video Reasoning Segmentation taaft The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reas… 2026-03-23 published
Learning Transferable Visual Models From Natural Language Supervision OpenAI State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object… 2021-02-26 published
Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory taaft Memory-augmented agents maintain compact user profiles throughout extended conversations, enabling… 2026-08-26 published
Learning When to Translate for Streaming Speech ByteDance How to find proper moments to generate partial sentence translation given a streaming speech input?… 2021-09-15 published
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry taaft Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them t… 2026-08-31 published